1 code implementation • ACL 2022 • Zhe Li, Luoyi Fu, Xinbing Wang, Haisong Zhang, Chenghu Zhou
However, most existing works either ignore the semantic information of relations or predict subjects and objects sequentially.
no code implementations • CCL 2020 • Xiuhong Li, Zhe Li, Jiabao Sheng, Wushour Slamu
There are major challenges of low-resource agglutinative text classification the lack of labeled data in a target domain and morphologic diversity of derivations in language structures.
no code implementations • 17 Feb 2025 • Sheng Fang, Kaiyu Li, Zhe Li, Jianli Zhao, Xingli Zhang
Image translation for change detection or classification in bi-temporal remote sensing images is unique.
no code implementations • 11 Feb 2025 • Xiao Wang, Ibrahim Alabdulmohsin, Daniel Salz, Zhe Li, Keran Rong, Xiaohua Zhai
We provide an empirical investigation of the potential of pre-training vision-language models on an unprecedented scale: 100 billion examples.
no code implementations • 4 Feb 2025 • Yixiao Chen, Shikun Sun, Jianshu Li, Ruoyu Li, Zhe Li, Junliang Xing
Adversarial attacks are widely used to evaluate model robustness, and in black-box scenarios, the transferability of these attacks becomes crucial.
1 code implementation • 7 Jan 2025 • Zhe Li, Man-Wai Mak, Mert Pilanci, Hung-Yi Lee, Helen Meng
Previous research has shown that the principal singular vectors of a pre-trained model's weight matrices capture critical knowledge.
no code implementations • 30 Dec 2024 • Yi Zhang, Weize Gao, Changtao Miao, Man Luo, Jianshu Li, Wenzhong Deng, Zhe Li, Bingyu Hu, Weibin Yao, Wenbo Zhou, Tao Gong, Qi Chu
In this paper, we present the solutions from the top 3 teams of the two tracks, to boost the research work in the field of image and audio-video forgery detection.
no code implementations • 18 Dec 2024 • Shenhao Zhu, Lingteng Qiu, Xiaodong Gu, Zhengyi Zhao, Chao Xu, Yuxiao He, Zhe Li, Xiaoguang Han, Yao Yao, Xun Cao, Siyu Zhu, Weihao Yuan, Zilong Dong, Hao Zhu
In the generation stage, we adopt a Diffusion Transformer (DiT) model to generate PBR materials, where both the specially designed multi-branch DiT and reference-based DiT blocks adopt a global attention mechanism to promote feature interaction and fusion between different views, thereby improving multi-view consistency.
1 code implementation • 18 Dec 2024 • Zheng Hu, Zhe Li, Ziyun Jiao, Satoshi Nakagawa, Jiawen Deng, Shimin Cai, Tao Zhou, Fuji Ren
In recent years, knowledge graphs have been integrated into recommender systems as item-side auxiliary information, enhancing recommendation accuracy.
no code implementations • 13 Dec 2024 • Zhe Li, Yisheng He, Lei Zhong, Weichao Shen, Qi Zuo, Lingteng Qiu, Zilong Dong, Laurence Tianruo Yang, Weihao Yuan
Generating motion sequences conforming to a target style while adhering to the given content prompts requires accommodating both the content and style.
no code implementations • 3 Dec 2024 • Lingteng Qiu, Shenhao Zhu, Qi Zuo, Xiaodong Gu, Yuan Dong, Junfei Zhang, Chao Xu, Zhe Li, Weihao Yuan, Liefeng Bo, GuanYing Chen, Zilong Dong
Generating animatable human avatars from a single image is essential for various digital human modeling applications.
no code implementations • 1 Dec 2024 • Zhipeng Lyu, Jinrong Su, Zhe Li, Xiang Li, Hanghang Yan, Lei Chen
Hybrid battery thermal management systems (HBTMS) combining active liquid cooling and passive phase change materials (PCM) cooling have shown a potential for the thermal management of lithium-ion batteries.
no code implementations • 15 Oct 2024 • Zhe Li, Xiangfei Qiu, Peng Chen, Yihang Wang, Hanyin Cheng, Yang Shu, Jilin Hu, Chenjuan Guo, Aoying Zhou, Qingsong Wen, Christian S. Jensen, Bin Yang
We propose a new benchmark, FoundTS, to enable thorough and fair evaluation and comparison of such models.
no code implementations • 9 Oct 2024 • Zhe Li, Weihao Yuan, Yisheng He, Lingteng Qiu, Shenhao Zhu, Xiaodong Gu, Weichao Shen, Yuan Dong, Zilong Dong, Laurence T. Yang
For captioning, we finetune a large language model with the language-informative motion features to develop a strong motion captioning model.
1 code implementation • 1 Oct 2024 • Wei Zhao, Zhe Li, Yige Li, Jun Sun
First, we demonstrate that benign features can be effectively made to function as adversarial suffixes, i. e., we develop a feature extraction method to extract sample-agnostic features from benign dataset in the form of suffixes and show that these suffixes may effectively compromise safety alignment.
1 code implementation • 30 Sep 2024 • Zhe Li, Wei Zhao, Yige Li, Jun Sun
Influence functions are important for quantifying the impact of individual training data points on a model's predictions.
no code implementations • 5 Sep 2024 • Zhe Li, Weitong Zhang, Sarah Cechnicka, Bernhard Kainz
While deep learning techniques have proven successful in image-related tasks, the exponentially increased data storage and computation costs become a significant challenge.
no code implementations • 29 Jul 2024 • Zhe Li, Ronghui Xu, Jilin Hu, Zhong Peng, Xi Lu, Chenjuan Guo, Bin Yang
By segmenting the limited buoy observational data temporally, encoding the buoys' locations spatially, and designing prompt templates, Orca capitalizes on the robust generalization ability of LLMs to estimate significant wave height effectively with limited data.
1 code implementation • 20 Jul 2024 • Fuhai Wang, Yunlong Huang, Zhanbo Feng, Rujing Xiong, Zhe Li, Chun Wang, Tiebin Mi, Robert Caiming Qiu, Zenan Ling
Reconfigurable intelligent surfaces (RISs) have emerged as a promising auxiliary technology for radio frequency imaging.
1 code implementation • 11 Jul 2024 • Yushuo Chen, Zerong Zheng, Zhe Li, Chao Xu, Yebin Liu
We present a novel pipeline for learning high-quality triangular human avatars from multi-view videos.
1 code implementation • 28 Jun 2024 • Zhangjing Yang, Dun Liu, Xin Wang, Zhe Li, Barathwaj Anandan, Yi Wu
This method achieves high video instance segmentation performance without manual video annotations, offering a cost-effective solution and new perspectives for video instance segmentation applications.
no code implementations • 27 Jun 2024 • Ivan Villa-Renteria, Mason L. Wang, Zachary Shah, Zhe Li, Soohyun Kim, Neelesh Ramachandran, Mert Pilanci
We also show that we can use the text instruction to control the generation of the inserted stem in terms of rhythm, dynamics, and genre, allowing us to modify the style of a single instrument in a full song while keeping the remaining instruments the same.
1 code implementation • 19 Jun 2024 • Zhe Li, Bernhard Kainz
We train a latent diffusion model and construct a new distilled synthetic dataset with a small number of human readable synthetic images.
no code implementations • 11 Jun 2024 • Tianqi Chen, Zhe Li, Weixiang Xu, Zeyu Zhu, Dong Li, Lu Tian, Emad Barsoum, Peisong Wang, Jian Cheng
The proposed OFF can incorporate semantic information and is insensitive to outliers.
1 code implementation • 3 Jun 2024 • Guanhua Huang, Yuchen Zhang, Zhe Li, Yongjian You, Mingze Wang, Zhouwang Yang
The SCRN employs a reconstruction network to add and remove noise from text, extracting a semantic representation that is robust to local perturbations.
1 code implementation • 28 May 2024 • Wei Zhao, Zhe Li, Yige Li, Ye Zhang, Jun Sun
Large language models (LLMs) are increasingly being adopted in a wide range of real-world applications.
1 code implementation • 24 May 2024 • Zhe Li, Bicheng Ying, Zidong Liu, Chaosheng Dong, Haibo Yang
This paper proposes a novel dimension-free communication algorithm - DeComFL, which leverages the zeroth-order optimization techniques and reduces the communication cost from $\mathscr{O}(d)$ to $\mathscr{O}(1)$ by transmitting only a constant number of scalar values between clients and the server in each round, regardless of the dimension $d$ of the model parameters.
Ranked #1 on
Classification
on BoolQ
no code implementations • 12 May 2024 • Siyou Lin, Zhe Li, Zhaoqi Su, Zerong Zheng, Hongwen Zhang, Yebin Liu
In the single-layer reconstruction stage, we propose a series of geometric constraints to reconstruct smooth surfaces and simultaneously obtain the segmentation between body and clothing.
no code implementations • 15 Apr 2024 • Jie zhou, Xin Chen, Hang Zhang, Zhe Li
Building on these results, we detail the automatic construction process of case knowledge graphs for judicial cases, enabling the assembly of knowledge graphs for hundreds of thousands of judgments.
1 code implementation • 12 Apr 2024 • Zhe Li, Haiwei Pan, Kejia Zhang, Yuhua Wang, Fengming Yu
Multi-modality image fusion (MMIF) aims to integrate complementary information from different modalities into a single fused image to represent the imaging scene and facilitate downstream visual tasks comprehensively.
no code implementations • CVPR 2024 • Yuxiao Liu, Zhe Li, Yebin Liu, Haoqian Wang
To adequately utilize the available image evidence in multi-view video-based avatar modeling, we propose TexVocab, a novel avatar representation that constructs a texture vocabulary and associates body poses with texture maps for animation.
no code implementations • 1 Mar 2024 • shiyi qi, Liangjian Wen, Yiduo Li, Yuanhang Yang, Zhe Li, Zhongwen Rao, Lujia Pan, Zenglin Xu
To substantiate this claim, we introduce the Cross-variable Decorrelation Aware feature Modeling (CDAM) for Channel-mixing approaches, aiming to refine Channel-mixing by minimizing redundant information between channels while enhancing relevant mutual information.
no code implementations • 27 Feb 2024 • Junshuo Liu, Yunlong Huang, Wei Yang, Zhe Li, Rujing Xiong, Tiebin Mi, Xin Shi, Robert C. Qiu
Human activity recognition (HAR) holds significant importance in smart homes, security, and healthcare.
1 code implementation • 23 Feb 2024 • Ziheng Jiang, Haibin Lin, Yinmin Zhong, Qi Huang, Yangrui Chen, Zhi Zhang, Yanghua Peng, Xiang Li, Cong Xie, Shibiao Nong, Yulu Jia, Sun He, Hongmin Chen, Zhihao Bai, Qi Hou, Shipeng Yan, Ding Zhou, Yiyao Sheng, Zhuo Jiang, Haohan Xu, Haoran Wei, Zhang Zhang, Pengfei Nie, Leqi Zou, Sida Zhao, Liang Xiang, Zherui Liu, Zhe Li, Xiaoying Jia, Jianxi Ye, Xin Jin, Xin Liu
Training LLMs at this scale brings unprecedented challenges to training efficiency and stability.
no code implementations • 3 Feb 2024 • Zhe Li, Ziyang Zhang, Jinglin Zhao, Zheng Wang, Bocheng Ren, Debin Liu, Laurence T. Yang
Experimental results demonstrate that our method enhances the expressive capacity of existing point cloud models and effectively addresses the issue of information leakage.
no code implementations • CVPR 2024 • Zhe Li, Laurence T. Yang, Bocheng Ren, Xin Nie, Zhangyang Gao, Cheng Tan, Stan Z. Li
The scarcity of annotated data has sparked significant interest in unsupervised pre-training methods that leverage medical reports as auxiliary signals for medical visual representation learning.
no code implementations • 30 Jan 2024 • Qingchen Wang, Zhe Li, Zdenka Babic, Wei Deng, Ljubiša Stanković, Danilo P. Mandic
However, applying this paradigm to illuminate the interpretability of complex-valued CNNs meets a formidable obstacle: the extension of matched filtering to a general class of noncircular complex-valued data, referred to here as the widely linear matched filter (WLMF), has been only implicit in the literature.
1 code implementation • CVPR 2024 • Zhe Li, Zhangyang Gao, Cheng Tan, Bocheng Ren, Laurence T. Yang, Stan Z. Li
Compared to models like Point-BERT MaskPoint and PointMAE our GPM achieves superior performance in point cloud understanding tasks.
1 code implementation • CVPR 2024 • Zhe Li, Zerong Zheng, Lizhen Wang, Yebin Liu
Overall our method can create lifelike avatars with dynamic realistic and generalized appearances.
1 code implementation • 13 Dec 2023 • Wei Zhao, Zhe Li, Jun Sun
Based on a layer-level causality analysis, we show that RLHF has the effect of overfitting a model to harmful prompts.
1 code implementation • CVPR 2024 • Zhanfeng Liao, Yuelang Xu, Zhe Li, Qijing Li, Boyao Zhou, Ruifeng Bai, Di Xu, Hongwen Zhang, Yebin Liu
To address the problem of dynamic hair modeling, we introduce a hybrid head model into our avatar representation based Gaussian Head Avatar and a training method that considers timing information and an occlusion perception module to model the non-rigid motion of hair.
1 code implementation • 27 Nov 2023 • Zhe Li, Yipengjing Sun, Zerong Zheng, Lizhen Wang, Shengping Zhang, Yebin Liu
To associate 3D Gaussians with the animatable avatar, we learn a parametric template from the input videos, and then parameterize the template on two front & back canonical Gaussian maps where each pixel represents a 3D Gaussian.
no code implementations • 14 Nov 2023 • Wenxi Zhang, Zhe Li, Weixi Li, Weisi Ma, Xinyi Chen, Sizhe Li
This paper introduces a robust, learning-based method for diagnosing the state of distribution network switchgear, which is crucial for maintaining the power quality for end users.
no code implementations • 10 Nov 2023 • Junshuo Liu, Fuhai Wang, Zhe Li, Rujing Xiong, Tiebin Mi, Robert Caiming Qiu
As a consequence, the accuracy of human activity recognition based on Wi-Fi signals is compromised.
no code implementations • 25 Oct 2023 • Zhe Li, Zhangyang Gao, Cheng Tan, Stan Z. Li, Laurence T. Yang
This model is versatile, allowing fine-tuning for downstream point cloud representation tasks, as well as unconditional and conditional generation tasks.
1 code implementation • 6 Oct 2023 • Glejdis Shkëmbi, Johanna P. Müller, Zhe Li, Katharina Breininger, Peter Schüffler, Bernhard Kainz
Breast cancer is a major concern for women's health globally, with axillary lymph node (ALN) metastasis identification being critical for prognosis evaluation and treatment guidance.
1 code implementation • 4 Oct 2023 • Rajkumar Vasudeva Raju, Zhe Li, Scott Linderman, Xaq Pitkow
Given a time series of neural activity during a perceptual inference task, our framework finds (i) the neural representation of relevant latent variables, (ii) interactions between these variables that define the brain's internal model of the world, and (iii) message-functions specifying the inference algorithm.
2 code implementations • 17 Jul 2023 • Ruichen Li, Haotian Ye, Du Jiang, Xuelan Wen, Chuwei Wang, Zhe Li, Xiang Li, Di He, Ji Chen, Weiluo Ren, LiWei Wang
Neural network-based variational Monte Carlo (NN-VMC) has emerged as a promising cutting-edge technique of ab initio quantum chemistry.
no code implementations • 30 May 2023 • Wenbin He, Jianxu Mao, Yaonan Wang, Zhe Li, Qiu Fang, Haotian Wu
To improve the performance in identifying the faults under strong noise for rotating machinery, this paper presents a dynamic feature reconstruction signal graph method, which plays the key role of the proposed end-to-end fault diagnosis model.
1 code implementation • 18 May 2023 • Zhe Li, shiyi qi, Yiduo Li, Zenglin Xu
In this paper, we thoroughly investigate the intrinsic effectiveness of recent approaches and make three key observations: 1) linear mapping is critical to prior long-term time series forecasting efforts; 2) RevIN (reversible normalization) and CI (Channel Independent) play a vital role in improving overall forecasting performance; and 3) linear mapping can effectively capture periodic features in time series and has robustness for different periods across channels when increasing the input horizon.
Ranked #1 on
Time Series Forecasting
on ETTh2 (720) Multivariate
1 code implementation • 4 May 2023 • Teng Wang, Jinrui Zhang, Junjie Fei, Hao Zheng, Yunlong Tang, Zhe Li, Mingqi Gao, Shanshan Zhao
Controllable image captioning is an emerging multimodal topic that aims to describe the image with natural language following human purpose, $\textit{e. g.}$, looking at the specified regions or telling in a particular text style.
1 code implementation • 25 Apr 2023 • Zhe Li, Zerong Zheng, Yuxiao Liu, Boyao Zhou, Yebin Liu
To this end, we present PoseVocab, a novel pose encoding method that encourages the network to discover the optimal pose embeddings for learning the dynamic human appearance.
1 code implementation • 24 Apr 2023 • Jinyu Yang, Mingqi Gao, Zhe Li, Shang Gao, Fangjing Wang, Feng Zheng
Therefore, in this report, we propose Track Anything Model (TAM), which achieves high-performance interactive tracking and segmentation in videos.
1 code implementation • ICCV 2023 • Zhendong Yang, Ailing Zeng, Zhe Li, Tianke Zhang, Chun Yuan, Yu Li
We decompose the KD loss and find the non-target loss from it forces the student's non-target logits to match the teacher's, but the sum of the two non-target logits is different, preventing them from being identical.
no code implementations • 16 Feb 2023 • Zhe Li, Honglong Chen, Zhichen Ni, Huajie Shao
Federated learning (FL) aims to collaboratively train the global model in a distributed manner by sharing the model parameters from local clients to a central server, thereby potentially protecting users' private information.
1 code implementation • 9 Feb 2023 • Zhe Li, Zhongwen Rao, Lujia Pan, Zenglin Xu
Specifically, we find that (1) attention is not necessary for capturing temporal dependencies, (2) the entanglement and redundancy in the capture of temporal and channel interaction affect the forecasting performance, and (3) it is important to model the mapping between the input and the prediction sequence.
1 code implementation • 21 Jan 2023 • Zhe Li, Zhongwen Rao, Lujia Pan, Pengyun Wang, Zenglin Xu
Multivariate Time Series forecasting has been an increasingly popular topic in various applications and scenarios.
Contrastive Learning
Multivariate Time Series Forecasting
+2
1 code implementation • CVPR 2023 • Jinyu Yang, Shang Gao, Zhe Li, Feng Zheng, Aleš Leonardis
However, current research on aerial perception has mainly focused on limited categories, such as pedestrian or vehicle, and most scenes are captured in urban environments from a birds-eye view.
no code implementations • 6 Nov 2022 • Shang Gao, Jinyu Yang, Zhe Li, Feng Zheng, Aleš Leonardis, Jingkuan Song
However, some existing RGBD trackers use the two modalities separately and thus some particularly useful shared information between them is ignored.
no code implementations • 29 Oct 2022 • Zhe Li, Man-Wai Mak, Helen Mei-Ling Meng
The challenges in applying contrastive learning to speaker verification (SV) are that the softmax-based contrastive loss lacks discriminative power and that the hard negative pairs can easily influence learning.
1 code implementation • 29 Oct 2022 • Zhe Li, Man-Wai Mak
A great challenge in speaker representation learning using deep models is to design learning objectives that can enhance the discrimination of unseen speakers under unseen domains.
no code implementations • 27 Oct 2022 • Jiabao Sheng, Yuanpeng Zhang, Jing Cai, Sai-Kit Lam, Zhe Li, Jiang Zhang, Xinzhi Teng
To improve the discriminative ability of the loss function, we incorporate a margin into the contrastive learning.
1 code implementation • 17 Sep 2022 • Sheng Fang, Kaiyu Li, Zhe Li
To verify the effectiveness of MetaChanger, we propose two derived models, ChangerAD and ChangerEx with simple interaction strategies: Aggregation-Distribution (AD) and "exchange".
Building change detection for remote sensing images
Change Detection
+1
1 code implementation • 6 Sep 2022 • Zhendong Yang, Zhe Li, Ailing Zeng, Zexian Li, Chun Yuan, Yu Li
In this paper, we explore the way of feature-based distillation for ViT.
1 code implementation • 22 Aug 2022 • Zhendong Yang, Zhe Li, Yuan Gong, Tianke Zhang, Shanshan Lao, Chun Yuan, Yu Li
Furthermore, we smooth students' target output to treat it as the soft target for training without teachers and propose a teacher-free new KD loss (tf-NKD).
no code implementations • 29 Jul 2022 • Jinyu Yang, Zhe Li, Feng Zheng, Aleš Leonardis, Jingkuan Song
Multi-modal tracking gains attention due to its ability to be more accurate and robust in complex scenarios compared to traditional RGB-based tracking.
Ranked #29 on
Rgb-T Tracking
on LasHeR
1 code implementation • 5 Jul 2022 • Zhe Li, Zerong Zheng, Hongwen Zhang, Chaonan Ji, Yebin Liu
Then given a monocular RGB video of this subject, our method integrates information from both the image observation and the avatar prior, and accordingly recon-structs high-fidelity 3D textured models with dynamic details regardless of the visibility.
3 code implementations • 3 May 2022 • Zhendong Yang, Zhe Li, Mingqi Shao, Dachuan Shi, Zehuan Yuan, Chun Yuan
The current distillation algorithm usually improves students' performance by imitating the output of the teacher.
1 code implementation • 26 Mar 2022 • Jinyu Yang, Zhe Li, Song Yan, Feng Zheng, Aleš Leonardis, Joni-Kristian Kämäräinen, Ling Shao
Particularly, we are the first to provide depth quality evaluation and analysis of tracking results in depth-friendly scenarios in RGBD tracking.
no code implementations • 23 Feb 2022 • Canjie Luo, Yuanzhi Zhu, Lianwen Jin, Zhe Li, Dezhi Peng
Specifically, we propose a style bank to parameterize the specific handwriting styles as latent vectors, which are input to a generator as style priors to achieve the corresponding handwritten styles.
no code implementations • 22 Feb 2022 • Zhe Li, Andreas S. Tolias, Xaq Pitkow
In this work we trained graph neural networks to fit time series from an example nonlinear dynamical system, the belief propagation algorithm.
no code implementations • 16 Feb 2022 • Zhichen Ni, Honglong Chen, Zhe Li, Xiaomeng Wang, Na Yan, Weifeng Liu, Feng Xia
The vehicles can offload the computation intensive tasks to the cloud to save the resource of edge.
no code implementations • 16 Feb 2022 • Zhu Wang, Honglong Chen, Zhe Li, Kai Lin, Nan Jiang, Feng Xia
Fortunately, context-aware recommender systems can alleviate the sparsity problem by making use of some auxiliary information, such as the information of both the users and items.
no code implementations • 16 Feb 2022 • Honglong Chen, Zhe Li, Zhu Wang, Zhichen Ni, Junjian Li, Ge Xu, Abdul Aziz, Feng Xia
As an effective way to alleviate information overload, recommender system can improve the quality of various services by adding application data generated by users on edge devices, such as visual and textual information, on the basis of sparse rating data.
1 code implementation • CVPR 2022 • Zhendong Yang, Zhe Li, Xiaohu Jiang, Yuan Gong, Zehuan Yuan, Danpei Zhao, Chun Yuan
Global distillation rebuilds the relation between different pixels and transfers it from teachers to students, compensating for missing global information in focal distillation.
Ranked #1 on
Knowledge Distillation
on MS COCO
no code implementations • 1 Oct 2021 • Chengyi Tu, Paolo DOdorico, Zhe Li, Samir Suweis
The sustainable use of common-pool resources (CPRs) is a major environmental governance challenge because of their possible over-exploitation.
no code implementations • ICCV 2021 • Yuxiang Zhang, Zhe Li, Liang An, Mengcheng Li, Tao Yu, Yebin Liu
Overall, we propose the first light-weight total capture system and achieves fast, robust and accurate multi-person total motion capture performance.
Ranked #2 on
3D Multi-Person Pose Estimation
on Shelf
1 code implementation • CVPR 2021 • Tianwei Wang, Yuanzhi Zhu, Lianwen Jin, Dezhi Peng, Zhe Li, Mengchao He, Yongpan Wang, Canjie Luo
Specifically, we integrate IFA into the two most prevailing text recognition streams (attention-based and CTC-based) and propose attention-guided dense prediction (ADP) and Extended CTC (ExCTC).
Optical Character Recognition
Optical Character Recognition (OCR)
+1
1 code implementation • 9 Jun 2021 • Sheng Fang, Kaiyu Li, Zhe Li
Aimed at both questions this paper proposes the salient positions-based attention scheme SPANet, which is inspired by some interesting observations on the attention maps and affinity matrices generated in self-attention scheme.
1 code implementation • 26 May 2021 • Chun-Ta Lu, Yun Zeng, Da-Cheng Juan, Yicheng Fan, Zhe Li, Jan Dlabal, Yi-Ting Chen, Arjun Gopalan, Allan Heydon, Chun-Sung Ferng, Reah Miyara, Ariel Fuxman, Futang Peng, Zhen Li, Tom Duerig, Andrew Tomkins
In this work, we propose CARLS, a novel framework for augmenting the capacity of existing deep learning frameworks by enabling multiple components -- model trainers, knowledge makers and knowledge banks -- to concertedly work together in an asynchronous fashion across hardware platforms.
2 code implementations • 27 Apr 2021 • Haotian Yan, Zhe Li, Weijian Li, Changhu Wang, Ming Wu, Chuang Zhang
It is also worth pointing that, given identical strong data augmentations, the performance improvement of ConTNet is more remarkable than that of ResNet.
2 code implementations • 20 Apr 2021 • Gido M. van de Ven, Zhe Li, Andreas S. Tolias
As a proof-of-principle, here we implement this strategy by training a variational autoencoder for each class to be learned and by using importance sampling to estimate the likelihoods p(x|y).
no code implementations • CVPR 2021 • Zhe Li, Tao Yu, Zerong Zheng, Kaiwen Guo, Yebin Liu
By contributing a novel reconstruction framework which contains pose-guided keyframe selection and robust implicit surface fusion, our method fully utilizes the advantages of both tracking-based methods and tracking-free inference methods, and finally enables the high-fidelity reconstruction of dynamic surface details even in the invisible regions.
1 code implementation • CVPR 2021 • Zhe Li, Yazan Abu Farha, Juergen Gall
To demonstrate the effectiveness of timestamp supervision, we propose an approach to train a segmentation model using only timestamps annotations.
Ranked #4 on
Weakly Supervised Action Localization
on GTEA
1 code implementation • 27 Oct 2020 • Kaiyu Li, Zhe Li, Sheng Fang
In this paper, we improve the semantic segmentation network UNet++ and propose a fully convolutional siamese network (Siam-NestedUNet) for change detection.
Change Detection
Change detection for remote sensing images
+2
no code implementations • 20 Jul 2020 • Zhe Li, Lianwen Jin, Songxuan Lai, Yecheng Zhu
Handwritten mathematical expression recognition (HMER) is an important research direction in handwriting recognition.
no code implementations • 18 May 2020 • Zechun Liu, Xiangyu Zhang, Zhiqiang Shen, Zhe Li, Yichen Wei, Kwang-Ting Cheng, Jian Sun
To tackle these three naturally different dimensions, we proposed a general framework by defining pruning as seeking the best pruning vector (i. e., the numerical value of layer-wise channel number, spacial size, depth) and construct a unique mapping from the pruning vector to the pruned network structures.
no code implementations • CVPR 2020 • Zhe Li, Tao Yu, Chuanyu Pan, Zerong Zheng, Yebin Liu
In this paper, we propose an efficient method for robust 3D self-portraits using a single RGBD camera.
no code implementations • 7 Mar 2020 • Zhe Li, Chunhua Sun, Chunli Liu, Xiayu Chen, Meng Wang, Yezheng Liu
To address these issues, we focus on semi-supervised outlier detection with few identified anomalies, in the hope of using limited labels to achieve high detection accuracy.
no code implementations • 2 Mar 2020 • Liang Jiang, Zujie Wen, Zhongping Liang, Yafang Wang, Gerard de Melo, Zhe Li, Liangzhuang Ma, Jiaxing Zhang, Xiaolong Li, Yuan Qi
The long-term teacher draws on snapshots from several epochs ago in order to provide steadfast guidance and to guarantee teacher--student differences, while the short-term one yields more up-to-date cues with the goal of enabling higher-quality updates.
1 code implementation • NeurIPS 2019 • Zhe Li, Wieland Brendel, Edgar Y. Walker, Erick Cobos, Taliah Muhammad, Jacob Reimer, Matthias Bethge, Fabian H. Sinz, Xaq Pitkow, Andreas S. Tolias
We propose to regularize CNNs using large-scale neuroscience data to learn more robust neural features in terms of representational similarity.
no code implementations • ICCV 2019 • Yuyin Zhou, Zhe Li, Song Bai, Chong Wang, Xinlei Chen, Mei Han, Elliot Fishman, Alan Yuille
Accurate multi-organ abdominal CT segmentation is essential to many clinical applications such as computer-aided intervention.
no code implementations • 28 Feb 2019 • Siyu Liao, Zhe Li, Liang Zhao, Qinru Qiu, Yanzhi Wang, Bo Yuan
Deep neural networks (DNNs), especially deep convolutional neural networks (CNNs), have emerged as the powerful technique in various machine learning applications.
no code implementations • 12 Dec 2018 • Zhe Li, Caiwen Ding, Siyue Wang, Wujie Wen, Youwei Zhuo, Chang Liu, Qinru Qiu, Wenyao Xu, Xue Lin, Xuehai Qian, Yanzhi Wang
It is a challenging task to have real-time, efficient, and accurate hardware RNN implementations because of the high sensitivity to imprecision accumulation and the requirement of special activation function implementations.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
no code implementations • NeurIPS 2018 • Mingrui Liu, Zhe Li, Xiaoyu Wang, Jin-Feng Yi, Tianbao Yang
Negative curvature descent (NCD) method has been utilized to design deterministic or stochastic algorithms for non-convex optimization aiming at finding second-order stationary points or local minima.
2 code implementations • 28 Sep 2018 • Yezheng Liu, Zhe Li, Chong Zhou, Yuanchun Jiang, Jianshan Sun, Meng Wang, Xiangnan He
In this paper, we approach outlier detection as a binary-classification issue by sampling potential outliers from a uniform reference distribution.
no code implementations • 30 Aug 2018 • Yan Yan, Tianbao Yang, Zhe Li, Qihang Lin, Yi Yang
However, their theoretical analysis of convergence of the training objective and the generalization error for prediction is still under-explored.
no code implementations • CVPR 2019 • Jian Ren, Zhe Li, Jianchao Yang, Ning Xu, Tianbao Yang, David J. Foran
In this paper, we propose an Ecologically-Inspired GENetic (EIGEN) approach that uses the concept of succession, extinction, mimicry, and gene duplication to search neural network structure from scratch with poorly initialized simple network and few constraints forced during the evolution, as we assume no prior knowledge about the task domain.
no code implementations • 3 Jun 2018 • Zhe Li, Xuehan Xiong, Zhou Ren, Ning Zhang, Xiaoyu Wang, Tianbao Yang
In this paper, we study how to design a genetic programming approach for optimizing the structure of a CNN for a given task under limited computational resources yet without imposing strong restrictions on the search space.
no code implementations • 10 May 2018 • Zhe Li, Ji Li, Ao Ren, Caiwen Ding, Jeffrey Draper, Qinru Qiu, Bo Yuan, Yanzhi Wang
Recently, Deep Convolutional Neural Network (DCNN) has achieved tremendous success in many machine learning applications.
no code implementations • 11 Apr 2018 • Ziyi Zhao, Krittaphat Pugdeethosapol, Sheng Lin, Zhe Li, Caiwen Ding, Yanzhi Wang, Qinru Qiu
The topic modeling discovers the latent topic probability of the given text documents.
no code implementations • 20 Mar 2018 • Zhe Li, Shuo Wang, Caiwen Ding, Qinru Qiu, Yanzhi Wang, Yun Liang
Recurrent Neural Networks (RNNs) are becoming increasingly important for time series-related applications which require efficient and real-time implementations.
no code implementations • 20 Mar 2018 • Zhe Li, Xiaolong Ma, Hongjia Li, Qiyuan An, Aditya Singh Rathore, Qinru Qiu, Wenyao Xu, Yanzhi Wang
It is of vital importance to enable 3D printers to identify the objects to be printed, so that the manufacturing procedure of an illegal weapon can be terminated at the early stage.
no code implementations • 14 Mar 2018 • Shuo Wang, Zhe Li, Caiwen Ding, Bo Yuan, Yanzhi Wang, Qinru Qiu, Yun Liang
The previous work proposes to use a pruning based compression technique to reduce the model size and thus speedups the inference on FPGAs.
no code implementations • 25 Feb 2018 • Kun Hu, Zhe Li, Ying Liu, Luyin Cheng, Qi Yang, Yan Li
In the first prediction part, we focus on predicting the downward trend, which is an earlier stage of the customer lifecycle compared to churn.
no code implementations • 18 Feb 2018 • Yanzhi Wang, Caiwen Ding, Zhe Li, Geng Yuan, Siyu Liao, Xiaolong Ma, Bo Yuan, Xuehai Qian, Jian Tang, Qinru Qiu, Xue Lin
Hardware accelerations of deep learning systems have been extensively investigated in industry and academia.
no code implementations • 15 Feb 2018 • Hongjia Li, Xiaolong Ma, Aditya Singh Rathore, Zhe Li, Qiyuan An, Chen Song, Wenyao Xu, Yanzhi Wang
The rapid development in additive manufacturing (AM), also known as 3D printing, has brought about potential risk and security issues along with significant benefits.
no code implementations • 3 Feb 2018 • Xiaolong Ma, Yi-Peng Zhang, Geng Yuan, Ao Ren, Zhe Li, Jie Han, Jingtong Hu, Yanzhi Wang
However, in these works, the memory design optimization is neglected for weight storage, which will inevitably result in large hardware cost.
11 code implementations • 22 Nov 2017 • Fangzhou Liao, Ming Liang, Zhe Li, Xiaolin Hu, Sen Song
The model consists of two modules.
1 code implementation • CVPR 2018 • Zhe Li, Chong Wang, Mei Han, Yuan Xue, Wei Wei, Li-Jia Li, Li Fei-Fei
Accurate identification and localization of abnormalities from radiology images play an integral part in clinical diagnosis and treatment planning.
no code implementations • 9 Sep 2017 • Tianbao Yang, Zhe Li, Lijun Zhang
In this paper, we present a simple analysis of {\bf fast rates} with {\it high probability} of {\bf empirical minimization} for {\it stochastic composite optimization} over a finite-dimensional bounded convex set with exponential concave loss functions and an arbitrary convex regularization.
no code implementations • 29 Aug 2017 • Caiwen Ding, Siyu Liao, Yanzhi Wang, Zhe Li, Ning Liu, Youwei Zhuo, Chao Wang, Xuehai Qian, Yu Bai, Geng Yuan, Xiaolong Ma, Yi-Peng Zhang, Jian Tang, Qinru Qiu, Xue Lin, Bo Yuan
As the size of DNNs continues to grow, it is critical to improve the energy efficiency and performance while maintaining accuracy.
no code implementations • 13 Jun 2017 • Zhe Li, Xiaoyu Wang, Xutao Lv, Tianbao Yang
By doing this, we show that previous deep CNNs such as GoogLeNet and Inception-type Nets can be compressed dramatically with marginal drop in performance.
no code implementations • 13 Mar 2017 • Ning Liu, Zhe Li, Zhiyuan Xu, Jielong Xu, Sheng Lin, Qinru Qiu, Jian Tang, Yanzhi Wang
Automatic decision-making approaches, such as reinforcement learning (RL), have been applied to (partially) solve the resource allocation problem adaptively in the cloud computing system.
no code implementations • 12 Mar 2017 • Ji Li, Zihao Yuan, Zhe Li, Caiwen Ding, Ao Ren, Qinru Qiu, Jeffrey Draper, Yanzhi Wang
Recently, Deep Convolutional Neural Networks (DCNNs) have made unprecedented progress, achieving the accuracy close to, or even better than human-level perception in various tasks.
no code implementations • ICML 2017 • Liang Zhao, Siyu Liao, Yanzhi Wang, Zhe Li, Jian Tang, Victor Pan, Bo Yuan
Recently low displacement rank (LDR) matrices, or so-called structured matrices, have been proposed to compress large-scale neural networks.
no code implementations • 18 Nov 2016 • Ao Ren, Ji Li, Zhe Li, Caiwen Ding, Xuehai Qian, Qinru Qiu, Bo Yuan, Yanzhi Wang
Stochastic Computing (SC), which uses bit-stream to represent a number within [-1, 1] by counting the number of ones in the bit-stream, has a high potential for implementing DCNNs with high scalability and ultra-low hardware footprint.
no code implementations • 12 Apr 2016 • Tianbao Yang, Qihang Lin, Zhe Li
This paper fills the gap between practice and theory by developing a basic convergence analysis of two stochastic momentum methods, namely stochastic heavy-ball method and the stochastic variant of Nesterov's accelerated gradient method.
no code implementations • NeurIPS 2016 • Zhe Li, Boqing Gong, Tianbao Yang
To exhibit the optimal dropout probabilities, we analyze the shallow learning with multinomial dropout and establish the risk bound for stochastic optimization.